© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43315
    Prev
    Next
    INDEX
    Explanations

    object or state

    np_acts-logits-general · gemini-2.5-flash-lite

    Fill in the blanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.29
     diligently
    0.26
     tabulated
    0.26
     as
    0.26
     appunto
    0.26
    ’
    0.25
     tangible
    0.25
     and
    0.25
    *
    0.25
    s
    0.24
    POSITIVE LOGITS
    piano
    0.28
     ظلم
    0.27
    కుంది
    0.27
     dissati
    0.26
     murderous
    0.26
    𒌋
    0.26
    armée
    0.25
    ВИ
    0.25
    ៣
    0.25
    อาหาร
    0.25
    Activations Density 0.024%

    No Known Activations